[x264-devel] [PATCH 02/29] aarch64: Set the function symbol prefix in a single location

Vittorio Giovara vittorio.giovara at gmail.com
Thu Feb 2 10:05:14 CET 2017


---
 common/aarch64/asm.S         |   8 +++-
 common/aarch64/bitstream-a.S |   2 +-
 common/aarch64/cabac-a.S     |  10 ++--
 common/aarch64/dct-a.S       | 106 +++++++++++++++++++++----------------------
 common/aarch64/deblock-a.S   |  36 +++++++--------
 common/aarch64/mc-a.S        | 104 +++++++++++++++++++++---------------------
 common/aarch64/pixel-a.S     |  92 ++++++++++++++++++-------------------
 common/aarch64/predict-a.S   |  66 +++++++++++++--------------
 common/aarch64/quant-a.S     |  44 +++++++++---------
 tools/checkasm-aarch64.S     |   4 +-
 10 files changed, 238 insertions(+), 234 deletions(-)

diff --git a/common/aarch64/asm.S b/common/aarch64/asm.S
index 1ec1beb..658a1dd 100644
--- a/common/aarch64/asm.S
+++ b/common/aarch64/asm.S
@@ -28,9 +28,9 @@
 #include "config.h"
 
 #ifdef PREFIX
-#   define EXTERN_ASM _
+#   define EXTERN_ASM _x264_
 #else
-#   define EXTERN_ASM
+#   define EXTERN_ASM x264_
 #endif
 
 #ifdef __ELF__
@@ -53,7 +53,11 @@
 
 .macro  function name, export=0, align=2
     .macro endfunc
+.if \export
+ELF     .size   EXTERN_ASM\name, . - EXTERN_ASM\name
+.else
 ELF     .size   \name, . - \name
+.endif
 FUNC    .endfunc
         .purgem endfunc
     .endm
diff --git a/common/aarch64/bitstream-a.S b/common/aarch64/bitstream-a.S
index b110bf5..f8ce798 100644
--- a/common/aarch64/bitstream-a.S
+++ b/common/aarch64/bitstream-a.S
@@ -25,7 +25,7 @@
 
 #include "asm.S"
 
-function x264_nal_escape_neon, export=1
+function nal_escape_neon, export=1
     movi        v0.16b,  #0xff
     movi        v4.16b,  #4
     mov         w3,  #3
diff --git a/common/aarch64/cabac-a.S b/common/aarch64/cabac-a.S
index ae967f7..7f8fa84 100644
--- a/common/aarch64/cabac-a.S
+++ b/common/aarch64/cabac-a.S
@@ -29,9 +29,9 @@
 // w11 holds x264_cabac_t.i_low
 // w12 holds x264_cabac_t.i_range
 
-function x264_cabac_encode_decision_asm, export=1
-    movrel      x8,  X(x264_cabac_range_lps)
-    movrel      x9,  X(x264_cabac_transition)
+function cabac_encode_decision_asm, export=1
+    movrel      x8,  X(cabac_range_lps)
+    movrel      x9,  X(cabac_transition)
     add         w10, w1, #CABAC_STATE
     ldrb        w3,  [x0,  x10]         // i_state
     ldr         w12, [x0,  #CABAC_I_RANGE]
@@ -101,7 +101,7 @@ cabac_putbyte:
     ret
 endfunc
 
-function x264_cabac_encode_bypass_asm, export=1
+function cabac_encode_bypass_asm, export=1
     ldr         w12, [x0, #CABAC_I_RANGE]
     ldr         w11, [x0, #CABAC_I_LOW]
     ldr         w2,  [x0, #CABAC_I_QUEUE]
@@ -114,7 +114,7 @@ function x264_cabac_encode_bypass_asm, export=1
     ret
 endfunc
 
-function x264_cabac_encode_terminal_asm, export=1
+function cabac_encode_terminal_asm, export=1
     ldr         w12, [x0, #CABAC_I_RANGE]
     ldr         w11, [x0, #CABAC_I_LOW]
     sub         w12, w12, #2
diff --git a/common/aarch64/dct-a.S b/common/aarch64/dct-a.S
index 37e3f0e..cab5b31 100644
--- a/common/aarch64/dct-a.S
+++ b/common/aarch64/dct-a.S
@@ -79,7 +79,7 @@ endconst
 .endm
 
 
-function x264_dct4x4dc_neon, export=1
+function dct4x4dc_neon, export=1
     ld1        {v0.4h,v1.4h,v2.4h,v3.4h}, [x0]
     movi        v31.4h, #1
     SUMSUB_AB   v4.4h,  v5.4h,  v0.4h,  v1.4h
@@ -102,7 +102,7 @@ function x264_dct4x4dc_neon, export=1
     ret
 endfunc
 
-function x264_idct4x4dc_neon, export=1
+function idct4x4dc_neon, export=1
     ld1        {v0.4h,v1.4h,v2.4h,v3.4h}, [x0]
     SUMSUB_AB   v4.4h,  v5.4h,  v0.4h,  v1.4h
     SUMSUB_AB   v6.4h,  v7.4h,  v2.4h,  v3.4h
@@ -131,7 +131,7 @@ endfunc
     sub         \v3, \v7, \v5
 .endm
 
-function x264_sub4x4_dct_neon, export=1
+function sub4x4_dct_neon, export=1
     mov         x3, #FENC_STRIDE
     mov         x4, #FDEC_STRIDE
     ld1        {v0.s}[0], [x1], x3
@@ -154,7 +154,7 @@ function x264_sub4x4_dct_neon, export=1
     ret
 endfunc
 
-function x264_sub8x4_dct_neon
+function sub8x4_dct_neon
     ld1        {v0.8b}, [x1], x3
     ld1        {v1.8b}, [x2], x4
     usubl       v16.8h, v0.8b,  v1.8b
@@ -193,34 +193,34 @@ function x264_sub8x4_dct_neon
     ret
 endfunc
 
-function x264_sub8x8_dct_neon, export=1
+function sub8x8_dct_neon, export=1
     mov         x5,  x30
     mov         x3, #FENC_STRIDE
     mov         x4, #FDEC_STRIDE
-    bl          x264_sub8x4_dct_neon
+    bl          sub8x4_dct_neon
     mov         x30, x5
-    b           x264_sub8x4_dct_neon
+    b           sub8x4_dct_neon
 endfunc
 
-function x264_sub16x16_dct_neon, export=1
+function sub16x16_dct_neon, export=1
     mov         x5,  x30
     mov         x3, #FENC_STRIDE
     mov         x4, #FDEC_STRIDE
-    bl          x264_sub8x4_dct_neon
-    bl          x264_sub8x4_dct_neon
+    bl          sub8x4_dct_neon
+    bl          sub8x4_dct_neon
     sub         x1, x1, #8*FENC_STRIDE-8
     sub         x2, x2, #8*FDEC_STRIDE-8
-    bl          x264_sub8x4_dct_neon
-    bl          x264_sub8x4_dct_neon
+    bl          sub8x4_dct_neon
+    bl          sub8x4_dct_neon
     sub         x1, x1, #8
     sub         x2, x2, #8
-    bl          x264_sub8x4_dct_neon
-    bl          x264_sub8x4_dct_neon
+    bl          sub8x4_dct_neon
+    bl          sub8x4_dct_neon
     sub         x1, x1, #8*FENC_STRIDE-8
     sub         x2, x2, #8*FDEC_STRIDE-8
-    bl          x264_sub8x4_dct_neon
+    bl          sub8x4_dct_neon
     mov         x30, x5
-    b           x264_sub8x4_dct_neon
+    b           sub8x4_dct_neon
 endfunc
 
 
@@ -255,7 +255,7 @@ endfunc
     SUMSUB_SHR2 2, v3.8h,  v5.8h,  v30.8h, v29.8h, v20.8h, v21.8h
 .endm
 
-function x264_sub8x8_dct8_neon, export=1
+function sub8x8_dct8_neon, export=1
     mov         x3, #FENC_STRIDE
     mov         x4, #FDEC_STRIDE
     ld1        {v16.8b}, [x1], x3
@@ -292,19 +292,19 @@ function x264_sub8x8_dct8_neon, export=1
     ret
 endfunc
 
-function x264_sub16x16_dct8_neon, export=1
+function sub16x16_dct8_neon, export=1
     mov         x7,  x30
-    bl          X(x264_sub8x8_dct8_neon)
+    bl          X(sub8x8_dct8_neon)
     sub         x1,  x1,  #FENC_STRIDE*8 - 8
     sub         x2,  x2,  #FDEC_STRIDE*8 - 8
-    bl          X(x264_sub8x8_dct8_neon)
+    bl          X(sub8x8_dct8_neon)
     sub         x1,  x1,  #8
     sub         x2,  x2,  #8
-    bl          X(x264_sub8x8_dct8_neon)
+    bl          X(sub8x8_dct8_neon)
     mov         x30, x7
     sub         x1,  x1,  #FENC_STRIDE*8 - 8
     sub         x2,  x2,  #FDEC_STRIDE*8 - 8
-    b           X(x264_sub8x8_dct8_neon)
+    b           X(sub8x8_dct8_neon)
 endfunc
 
 
@@ -317,7 +317,7 @@ endfunc
     add         \d6, \d6, \d1
 .endm
 
-function x264_add4x4_idct_neon, export=1
+function add4x4_idct_neon, export=1
     mov         x2, #FDEC_STRIDE
     ld1        {v0.4h,v1.4h,v2.4h,v3.4h}, [x1]
 
@@ -357,7 +357,7 @@ function x264_add4x4_idct_neon, export=1
     ret
 endfunc
 
-function x264_add8x4_idct_neon, export=1
+function add8x4_idct_neon, export=1
     ld1        {v0.8h,v1.8h}, [x1], #32
     ld1        {v2.8h,v3.8h}, [x1], #32
     transpose   v20.2d, v21.2d, v0.2d, v2.2d
@@ -398,29 +398,29 @@ function x264_add8x4_idct_neon, export=1
     ret
 endfunc
 
-function x264_add8x8_idct_neon, export=1
+function add8x8_idct_neon, export=1
     mov             x2, #FDEC_STRIDE
     mov             x5,  x30
-    bl              X(x264_add8x4_idct_neon)
+    bl              X(add8x4_idct_neon)
     mov             x30, x5
-    b               X(x264_add8x4_idct_neon)
+    b               X(add8x4_idct_neon)
 endfunc
 
-function x264_add16x16_idct_neon, export=1
+function add16x16_idct_neon, export=1
     mov             x2, #FDEC_STRIDE
     mov             x5,  x30
-    bl              X(x264_add8x4_idct_neon)
-    bl              X(x264_add8x4_idct_neon)
+    bl              X(add8x4_idct_neon)
+    bl              X(add8x4_idct_neon)
     sub             x0, x0, #8*FDEC_STRIDE-8
-    bl              X(x264_add8x4_idct_neon)
-    bl              X(x264_add8x4_idct_neon)
+    bl              X(add8x4_idct_neon)
+    bl              X(add8x4_idct_neon)
     sub             x0, x0, #8
-    bl              X(x264_add8x4_idct_neon)
-    bl              X(x264_add8x4_idct_neon)
+    bl              X(add8x4_idct_neon)
+    bl              X(add8x4_idct_neon)
     sub             x0, x0, #8*FDEC_STRIDE-8
-    bl              X(x264_add8x4_idct_neon)
+    bl              X(add8x4_idct_neon)
     mov             x30, x5
-    b               X(x264_add8x4_idct_neon)
+    b               X(add8x4_idct_neon)
 endfunc
 
 .macro IDCT8_1D type
@@ -446,7 +446,7 @@ endfunc
     SUMSUB_AB   v19.8h, v20.8h, v2.8h,  v20.8h
 .endm
 
-function x264_add8x8_idct8_neon, export=1
+function add8x8_idct8_neon, export=1
     mov         x2,  #FDEC_STRIDE
     ld1        {v16.8h,v17.8h}, [x1], #32
     ld1        {v18.8h,v19.8h}, [x1], #32
@@ -503,19 +503,19 @@ function x264_add8x8_idct8_neon, export=1
     ret
 endfunc
 
-function x264_add16x16_idct8_neon, export=1
+function add16x16_idct8_neon, export=1
     mov             x7,  x30
-    bl              X(x264_add8x8_idct8_neon)
+    bl              X(add8x8_idct8_neon)
     sub             x0,  x0,  #8*FDEC_STRIDE-8
-    bl              X(x264_add8x8_idct8_neon)
+    bl              X(add8x8_idct8_neon)
     sub             x0,  x0,  #8
-    bl              X(x264_add8x8_idct8_neon)
+    bl              X(add8x8_idct8_neon)
     sub             x0,  x0,  #8*FDEC_STRIDE-8
     mov             x30, x7
-    b               X(x264_add8x8_idct8_neon)
+    b               X(add8x8_idct8_neon)
 endfunc
 
-function x264_add8x8_idct_dc_neon, export=1
+function add8x8_idct_dc_neon, export=1
     mov         x2,  #FDEC_STRIDE
     ld1        {v16.4h}, [x1]
     ld1        {v0.8b}, [x0], x2
@@ -605,7 +605,7 @@ endfunc
     st1         {v7.16b}, [x2], x3
 .endm
 
-function x264_add16x16_idct_dc_neon, export=1
+function add16x16_idct_dc_neon, export=1
     mov         x2,  x0
     mov         x3,  #FDEC_STRIDE
 
@@ -640,7 +640,7 @@ endfunc
     add         \dst\().8h, \dst\().8h, \t3\().8h
 .endm
 
-function x264_sub8x8_dct_dc_neon, export=1
+function sub8x8_dct_dc_neon, export=1
     mov             x3,  #FENC_STRIDE
     mov             x4,  #FDEC_STRIDE
 
@@ -660,7 +660,7 @@ function x264_sub8x8_dct_dc_neon, export=1
     ret
 endfunc
 
-function x264_sub8x16_dct_dc_neon, export=1
+function sub8x16_dct_dc_neon, export=1
     mov             x3,  #FENC_STRIDE
     mov             x4,  #FDEC_STRIDE
     sub4x4x2_dct_dc  v0, v16, v17, v18, v19, v20, v21, v22, v23
@@ -689,7 +689,7 @@ function x264_sub8x16_dct_dc_neon, export=1
     ret
 endfunc
 
-function x264_zigzag_interleave_8x8_cavlc_neon, export=1
+function zigzag_interleave_8x8_cavlc_neon, export=1
     mov        x3,  #7
     movi       v31.4s, #1
     ld4        {v0.8h,v1.8h,v2.8h,v3.8h}, [x1],  #64
@@ -718,7 +718,7 @@ function x264_zigzag_interleave_8x8_cavlc_neon, export=1
     ret
 endfunc
 
-function x264_zigzag_scan_4x4_frame_neon, export=1
+function zigzag_scan_4x4_frame_neon, export=1
     movrel      x2, scan4x4_frame
     ld1        {v0.16b,v1.16b}, [x1]
     ld1        {v16.16b,v17.16b}, [x2]
@@ -729,7 +729,7 @@ function x264_zigzag_scan_4x4_frame_neon, export=1
 endfunc
 
 .macro zigzag_sub_4x4 f ac
-function x264_zigzag_sub_4x4\ac\()_\f\()_neon, export=1
+function zigzag_sub_4x4\ac\()_\f\()_neon, export=1
     mov         x9,  #FENC_STRIDE
     mov         x4,  #FDEC_STRIDE
     movrel      x5,  sub4x4_\f
@@ -772,7 +772,7 @@ zigzag_sub_4x4 field, ac
 zigzag_sub_4x4 frame
 zigzag_sub_4x4 frame, ac
 
-function x264_zigzag_scan_4x4_field_neon, export=1
+function zigzag_scan_4x4_field_neon, export=1
     movrel      x2, scan4x4_field
     ld1        {v0.8h,v1.8h},   [x1]
     ld1        {v16.16b},       [x2]
@@ -781,7 +781,7 @@ function x264_zigzag_scan_4x4_field_neon, export=1
     ret
 endfunc
 
-function x264_zigzag_scan_8x8_frame_neon, export=1
+function zigzag_scan_8x8_frame_neon, export=1
     movrel      x2,  scan8x8_frame
     ld1        {v0.8h,v1.8h},   [x1], #32
     ld1        {v2.8h,v3.8h},   [x1], #32
@@ -841,7 +841,7 @@ const scan8x8_frame, align=5
     .byte T(7,5), T(7,6), T(6,7), T(7,7)
 endconst
 
-function x264_zigzag_scan_8x8_field_neon, export=1
+function zigzag_scan_8x8_field_neon, export=1
     movrel      x2,  scan8x8_field
     ld1        {v0.8h,v1.8h},   [x1], #32
     ld1        {v2.8h,v3.8h},   [x1], #32
@@ -868,7 +868,7 @@ function x264_zigzag_scan_8x8_field_neon, export=1
 endfunc
 
 .macro zigzag_sub8x8 f
-function x264_zigzag_sub_8x8_\f\()_neon, export=1
+function zigzag_sub_8x8_\f\()_neon, export=1
     movrel      x4,  sub8x8_\f
     mov         x5,  #FENC_STRIDE
     mov         x6,  #FDEC_STRIDE
diff --git a/common/aarch64/deblock-a.S b/common/aarch64/deblock-a.S
index 3675e94..56090dc 100644
--- a/common/aarch64/deblock-a.S
+++ b/common/aarch64/deblock-a.S
@@ -108,7 +108,7 @@
     sqxtun2         v0.16b,  v24.8h
 .endm
 
-function x264_deblock_v_luma_neon, export=1
+function deblock_v_luma_neon, export=1
     h264_loop_filter_start
 
     ld1             {v0.16b},  [x0], x1
@@ -131,7 +131,7 @@ function x264_deblock_v_luma_neon, export=1
     ret
 endfunc
 
-function x264_deblock_h_luma_neon, export=1
+function deblock_h_luma_neon, export=1
     h264_loop_filter_start
 
     sub             x0,  x0,  #4
@@ -302,7 +302,7 @@ endfunc
     bit             v2.16b, v26.16b,  v18.16b  // q2'_2
 .endm
 
-function x264_deblock_v_luma_intra_neon, export=1
+function deblock_v_luma_intra_neon, export=1
     h264_loop_filter_start_intra
 
     ld1             {v0.16b},  [x0], x1 // q0
@@ -328,7 +328,7 @@ function x264_deblock_v_luma_intra_neon, export=1
     ret
 endfunc
 
-function x264_deblock_h_luma_intra_neon, export=1
+function deblock_h_luma_intra_neon, export=1
     h264_loop_filter_start_intra
 
     sub             x0,  x0,  #4
@@ -421,7 +421,7 @@ endfunc
     sqxtun2         v0.16b,  v23.8h
 .endm
 
-function x264_deblock_v_chroma_neon, export=1
+function deblock_v_chroma_neon, export=1
     h264_loop_filter_start
 
     sub             x0,  x0,  x1, lsl #1
@@ -439,7 +439,7 @@ function x264_deblock_v_chroma_neon, export=1
     ret
 endfunc
 
-function x264_deblock_h_chroma_neon, export=1
+function deblock_h_chroma_neon, export=1
     h264_loop_filter_start
 
     sub             x0,  x0,  #4
@@ -472,7 +472,7 @@ deblock_h_chroma:
     ret
 endfunc
 
-function x264_deblock_h_chroma_422_neon, export=1
+function deblock_h_chroma_422_neon, export=1
     add             x5,  x0,  x1
     sub             x0,  x0,  #4
     add             x1,  x1,  x1
@@ -516,7 +516,7 @@ endfunc
     sqxtun          v17.8b,  v22.8h
 .endm
 
-function x264_deblock_h_chroma_mbaff_neon, export=1
+function deblock_h_chroma_mbaff_neon, export=1
     h264_loop_filter_start
 
     sub             x4,  x0,  #4
@@ -575,7 +575,7 @@ endfunc
     bit             v17.16b, v25.16b, v26.16b
 .endm
 
-function x264_deblock_v_chroma_intra_neon, export=1
+function deblock_v_chroma_intra_neon, export=1
     h264_loop_filter_start_intra
 
     sub             x0,  x0,  x1, lsl #1
@@ -593,7 +593,7 @@ function x264_deblock_v_chroma_intra_neon, export=1
     ret
 endfunc
 
-function x264_deblock_h_chroma_intra_mbaff_neon, export=1
+function deblock_h_chroma_intra_mbaff_neon, export=1
     h264_loop_filter_start_intra
 
     sub             x4,  x0,  #4
@@ -615,7 +615,7 @@ function x264_deblock_h_chroma_intra_mbaff_neon, export=1
     ret
 endfunc
 
-function x264_deblock_h_chroma_intra_neon, export=1
+function deblock_h_chroma_intra_neon, export=1
     h264_loop_filter_start_intra
 
     sub             x4,  x0,  #4
@@ -645,7 +645,7 @@ function x264_deblock_h_chroma_intra_neon, export=1
     ret
 endfunc
 
-function x264_deblock_h_chroma_422_intra_neon, export=1
+function deblock_h_chroma_422_intra_neon, export=1
     h264_loop_filter_start_intra
 
     sub             x4,  x0,  #4
@@ -697,12 +697,12 @@ function x264_deblock_h_chroma_422_intra_neon, export=1
     ret
 endfunc
 
-//static void deblock_strength_c( uint8_t nnz[X264_SCAN8_SIZE],
-//                                int8_t ref[2][X264_SCAN8_LUMA_SIZE],
-//                                int16_t mv[2][X264_SCAN8_LUMA_SIZE][2],
-//                                uint8_t bs[2][8][4], int mvy_limit,
-//                                int bframe )
-function x264_deblock_strength_neon, export=1
+// void deblock_strength( uint8_t nnz[X264_SCAN8_SIZE],
+//                        int8_t ref[2][X264_SCAN8_LUMA_SIZE],
+//                        int16_t mv[2][X264_SCAN8_LUMA_SIZE][2],
+//                        uint8_t bs[2][8][4], int mvy_limit,
+//                        int bframe )
+function deblock_strength_neon, export=1
     movi        v4.16b, #0
     lsl         w4,  w4,  #8
     add         x3,  x3,  #32
diff --git a/common/aarch64/mc-a.S b/common/aarch64/mc-a.S
index 1d4c8fd..179215f 100644
--- a/common/aarch64/mc-a.S
+++ b/common/aarch64/mc-a.S
@@ -31,7 +31,7 @@
 // note: prefetch stuff assumes 64-byte cacheline
 
 // void prefetch_ref( uint8_t *pix, intptr_t stride, int parity )
-function x264_prefetch_ref_aarch64, export=1
+function prefetch_ref_aarch64, export=1
     cmp         w2,  #1
     csel        x2,  xzr, x1, eq
     add         x0,  x0,  #64
@@ -54,8 +54,8 @@ endfunc
 
 // void prefetch_fenc( uint8_t *pix_y,  intptr_t stride_y,
 //                     uint8_t *pix_uv, intptr_t stride_uv, int mb_x )
-.macro x264_prefetch_fenc sub
-function x264_prefetch_fenc_\sub\()_aarch64, export=1
+.macro prefetch_fenc sub
+function prefetch_fenc_\sub\()_aarch64, export=1
     and         w6,  w5,  #3
     and         w7,  w5,  #3
     mul         x6,  x6,  x1
@@ -82,14 +82,14 @@ function x264_prefetch_fenc_\sub\()_aarch64, export=1
 endfunc
 .endm
 
-x264_prefetch_fenc 420
-x264_prefetch_fenc 422
+prefetch_fenc 420
+prefetch_fenc 422
 
 // void pixel_avg( uint8_t *dst,  intptr_t dst_stride,
 //                 uint8_t *src1, intptr_t src1_stride,
 //                 uint8_t *src2, intptr_t src2_stride, int weight );
 .macro AVGH w h
-function x264_pixel_avg_\w\()x\h\()_neon, export=1
+function pixel_avg_\w\()x\h\()_neon, export=1
     mov         w10, #64
     cmp         w6,  #32
     mov         w9, #\h
@@ -292,7 +292,7 @@ function pixel_avg_w16_neon
     ret
 endfunc
 
-function x264_pixel_avg2_w4_neon, export=1
+function pixel_avg2_w4_neon, export=1
 1:
     subs        w5,  w5,  #2
     ld1        {v0.s}[0],  [x2], x3
@@ -307,7 +307,7 @@ function x264_pixel_avg2_w4_neon, export=1
     ret
 endfunc
 
-function x264_pixel_avg2_w8_neon, export=1
+function pixel_avg2_w8_neon, export=1
 1:
     subs        w5,  w5,  #2
     ld1        {v0.8b}, [x2], x3
@@ -322,7 +322,7 @@ function x264_pixel_avg2_w8_neon, export=1
     ret
 endfunc
 
-function x264_pixel_avg2_w16_neon, export=1
+function pixel_avg2_w16_neon, export=1
 1:
     subs        w5,  w5,  #2
     ld1        {v0.16b}, [x2], x3
@@ -337,7 +337,7 @@ function x264_pixel_avg2_w16_neon, export=1
     ret
 endfunc
 
-function x264_pixel_avg2_w20_neon, export=1
+function pixel_avg2_w20_neon, export=1
     sub         x1,  x1,  #16
 1:
     subs        w5,  w5,  #2
@@ -373,7 +373,7 @@ endfunc
 
 // void mc_weight( uint8_t *src, intptr_t src_stride, uint8_t *dst,
 //                 intptr_t dst_stride, const x264_weight_t *weight, int h )
-function x264_mc_weight_w20_neon, export=1
+function mc_weight_w20_neon, export=1
     weight_prologue full
     sub         x1,  x1,  #16
 1:
@@ -409,7 +409,7 @@ function x264_mc_weight_w20_neon, export=1
     ret
 endfunc
 
-function x264_mc_weight_w16_neon, export=1
+function mc_weight_w16_neon, export=1
     weight_prologue full
 weight16_loop:
 1:
@@ -438,7 +438,7 @@ weight16_loop:
     ret
 endfunc
 
-function x264_mc_weight_w8_neon, export=1
+function mc_weight_w8_neon, export=1
     weight_prologue full
 1:
     subs        w9,  w9,  #2
@@ -458,7 +458,7 @@ function x264_mc_weight_w8_neon, export=1
     ret
 endfunc
 
-function x264_mc_weight_w4_neon, export=1
+function mc_weight_w4_neon, export=1
     weight_prologue full
 1:
     subs        w9,  w9,  #2
@@ -474,7 +474,7 @@ function x264_mc_weight_w4_neon, export=1
     ret
 endfunc
 
-function x264_mc_weight_w20_nodenom_neon, export=1
+function mc_weight_w20_nodenom_neon, export=1
     weight_prologue nodenom
     sub         x1,  x1,  #16
 1:
@@ -505,7 +505,7 @@ function x264_mc_weight_w20_nodenom_neon, export=1
     ret
 endfunc
 
-function x264_mc_weight_w16_nodenom_neon, export=1
+function mc_weight_w16_nodenom_neon, export=1
     weight_prologue nodenom
 1:
     subs        w9,  w9,  #2
@@ -529,7 +529,7 @@ function x264_mc_weight_w16_nodenom_neon, export=1
     ret
 endfunc
 
-function x264_mc_weight_w8_nodenom_neon, export=1
+function mc_weight_w8_nodenom_neon, export=1
     weight_prologue nodenom
 1:
     subs        w9,  w9,  #2
@@ -547,7 +547,7 @@ function x264_mc_weight_w8_nodenom_neon, export=1
     ret
 endfunc
 
-function x264_mc_weight_w4_nodenom_neon, export=1
+function mc_weight_w4_nodenom_neon, export=1
     weight_prologue nodenom
 1:
     subs        w9,  w9,  #2
@@ -568,7 +568,7 @@ endfunc
 .endm
 
 .macro weight_simple name op
-function x264_mc_weight_w20_\name\()_neon, export=1
+function mc_weight_w20_\name\()_neon, export=1
     weight_simple_prologue
 1:
     subs        w5,  w5,  #2
@@ -588,7 +588,7 @@ function x264_mc_weight_w20_\name\()_neon, export=1
     ret
 endfunc
 
-function x264_mc_weight_w16_\name\()_neon, export=1
+function mc_weight_w16_\name\()_neon, export=1
     weight_simple_prologue
 1:
     subs        w5,  w5,  #2
@@ -602,7 +602,7 @@ function x264_mc_weight_w16_\name\()_neon, export=1
     ret
 endfunc
 
-function x264_mc_weight_w8_\name\()_neon, export=1
+function mc_weight_w8_\name\()_neon, export=1
     weight_simple_prologue
 1:
     subs        w5,  w5,  #2
@@ -616,7 +616,7 @@ function x264_mc_weight_w8_\name\()_neon, export=1
     ret
 endfunc
 
-function x264_mc_weight_w4_\name\()_neon, export=1
+function mc_weight_w4_\name\()_neon, export=1
     weight_simple_prologue
 1:
     subs        w5,  w5,  #2
@@ -635,7 +635,7 @@ weight_simple offsetsub, uqsub
 
 
 // void mc_copy( uint8_t *dst, intptr_t dst_stride, uint8_t *src, intptr_t src_stride, int height )
-function x264_mc_copy_w4_neon, export=1
+function mc_copy_w4_neon, export=1
 1:
     subs        w4,  w4,  #4
     ld1        {v0.s}[0],  [x2],  x3
@@ -650,7 +650,7 @@ function x264_mc_copy_w4_neon, export=1
     ret
 endfunc
 
-function x264_mc_copy_w8_neon, export=1
+function mc_copy_w8_neon, export=1
 1:  subs        w4,  w4,  #4
     ld1        {v0.8b},  [x2],  x3
     ld1        {v1.8b},  [x2],  x3
@@ -664,7 +664,7 @@ function x264_mc_copy_w8_neon, export=1
     ret
 endfunc
 
-function x264_mc_copy_w16_neon, export=1
+function mc_copy_w16_neon, export=1
 1:  subs        w4,  w4,  #4
     ld1        {v0.16b}, [x2],  x3
     ld1        {v1.16b}, [x2],  x3
@@ -678,11 +678,11 @@ function x264_mc_copy_w16_neon, export=1
     ret
 endfunc
 
-// void x264_mc_chroma_neon( uint8_t *dst_u, uint8_t *dst_v,
-//                           intptr_t i_dst_stride,
-//                           uint8_t *src, intptr_t i_src_stride,
-//                           int dx, int dy, int i_width, int i_height );
-function x264_mc_chroma_neon, export=1
+// void mc_chroma( uint8_t *dst_u, uint8_t *dst_v,
+//                 intptr_t i_dst_stride,
+//                 uint8_t *src, intptr_t i_src_stride,
+//                 int dx, int dy, int i_width, int i_height );
+function mc_chroma_neon, export=1
     ldr         w15, [sp]               // height
     sbfx        x12, x6,  #3,  #29      // asr(3) and sign extend
     sbfx        x11, x5,  #3,  #29      // asr(3) and sign extend
@@ -1016,9 +1016,9 @@ function mc_chroma_w8_neon
     ret
 endfunc
 
-//void hpel_filter( pixel *dsth, pixel *dstv, pixel *dstc, pixel *src,
-//                  intptr_t stride, int width, int height, int16_t *buf )
-function x264_hpel_filter_neon, export=1
+// void hpel_filter( pixel *dsth, pixel *dstv, pixel *dstc, pixel *src,
+//                   intptr_t stride, int width, int height, int16_t *buf )
+function hpel_filter_neon, export=1
     ubfm        x9,  x3,  #0,  #3
     add         w15, w5,  w9
     sub         x13, x3,  x9            // align src
@@ -1158,7 +1158,7 @@ endfunc
 // frame_init_lowres_core( uint8_t *src0, uint8_t *dst0, uint8_t *dsth,
 //                         uint8_t *dstv, uint8_t *dstc, intptr_t src_stride,
 //                         intptr_t dst_stride, int width, int height )
-function x264_frame_init_lowres_core_neon, export=1
+function frame_init_lowres_core_neon, export=1
     ldr         w8,  [sp]
     sub         x10, x6,  w7, uxtw      // dst_stride - width
     and         x10, x10, #~15
@@ -1233,12 +1233,12 @@ function x264_frame_init_lowres_core_neon, export=1
     ret
 endfunc
 
-function x264_load_deinterleave_chroma_fenc_neon, export=1
+function load_deinterleave_chroma_fenc_neon, export=1
     mov         x4,  #FENC_STRIDE/2
     b           load_deinterleave_chroma
 endfunc
 
-function x264_load_deinterleave_chroma_fdec_neon, export=1
+function load_deinterleave_chroma_fdec_neon, export=1
     mov         x4,  #FDEC_STRIDE/2
 load_deinterleave_chroma:
     ld2        {v0.8b,v1.8b}, [x1], x2
@@ -1253,7 +1253,7 @@ load_deinterleave_chroma:
     ret
 endfunc
 
-function x264_plane_copy_core_neon, export=1
+function plane_copy_core_neon, export=1
     add         w8,  w4,  #15 // 32-bit write clears the upper 32-bit the register
     and         w4,  w8,  #~15
     // safe use of the full reg since negative width makes no sense
@@ -1282,7 +1282,7 @@ function x264_plane_copy_core_neon, export=1
     ret
 endfunc
 
-function x264_plane_copy_swap_core_neon, export=1
+function plane_copy_swap_core_neon, export=1
     lsl         w4,  w4,  #1
     sub         x1,  x1,  x4
     sub         x3,  x3,  x4
@@ -1310,7 +1310,7 @@ function x264_plane_copy_swap_core_neon, export=1
     ret
 endfunc
 
-function x264_plane_copy_deinterleave_neon, export=1
+function plane_copy_deinterleave_neon, export=1
     add         w9,  w6,  #15
     and         w9,  w9,  #0xfffffff0
     sub         x1,  x1,  x9
@@ -1349,7 +1349,7 @@ endfunc
     b.gt            1b
 .endm
 
-function x264_plane_copy_deinterleave_rgb_neon, export=1
+function plane_copy_deinterleave_rgb_neon, export=1
 #if SYS_MACOSX
     ldr             w8,  [sp]
     ldp             w9,  w10, [sp, #4]
@@ -1381,7 +1381,7 @@ function x264_plane_copy_deinterleave_rgb_neon, export=1
     ret
 endfunc
 
-function x264_plane_copy_interleave_core_neon, export=1
+function plane_copy_interleave_core_neon, export=1
     add         w9,  w6,  #15
     and         w9,  w9,  #0xfffffff0
     sub         x1,  x1,  x9,  lsl #1
@@ -1404,7 +1404,7 @@ function x264_plane_copy_interleave_core_neon, export=1
     ret
 endfunc
 
-function x264_store_interleave_chroma_neon, export=1
+function store_interleave_chroma_neon, export=1
     mov             x5,  #FDEC_STRIDE
 1:
     ld1        {v0.8b}, [x2], x5
@@ -1431,7 +1431,7 @@ endfunc
     add         v0.8h,  v0.8h,  v5.8h
 .endm
 
-function x264_integral_init4h_neon, export=1
+function integral_init4h_neon, export=1
     sub         x3,  x0,  x2, lsl #1
     ld1        {v6.8b,v7.8b}, [x1], #16
 1:
@@ -1466,7 +1466,7 @@ endfunc
     add         v0.8h,  v0.8h,  \s\().8h
 .endm
 
-function x264_integral_init8h_neon, export=1
+function integral_init8h_neon, export=1
     sub         x3,  x0,  x2, lsl #1
     ld1        {v16.8b,v17.8b}, [x1], #16
 1:
@@ -1483,7 +1483,7 @@ function x264_integral_init8h_neon, export=1
     ret
 endfunc
 
-function x264_integral_init4v_neon, export=1
+function integral_init4v_neon, export=1
     mov         x3,  x0
     add         x4,  x0,  x2,  lsl #3
     add         x8,  x0,  x2,  lsl #4
@@ -1518,7 +1518,7 @@ function x264_integral_init4v_neon, export=1
     ret
 endfunc
 
-function x264_integral_init8v_neon, export=1
+function integral_init8v_neon, export=1
     add         x2,  x0,  x1,  lsl #4
     sub         x1,  x1,  #8
     ands        x3,  x1,  #16 - 1
@@ -1542,7 +1542,7 @@ function x264_integral_init8v_neon, export=1
     ret
 endfunc
 
-function x264_mbtree_propagate_cost_neon, export=1
+function mbtree_propagate_cost_neon, export=1
     ld1r        {v5.4s},  [x5]
 8:
     subs        w6,  w6,  #8
@@ -1593,7 +1593,7 @@ const pw_0to15, align=5
     .short 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15
 endconst
 
-function x264_mbtree_propagate_list_internal_neon, export=1
+function mbtree_propagate_list_internal_neon, export=1
     movrel      x11,  pw_0to15
     dup         v31.8h,  w4             // bipred_weight
     movi        v30.8h,  #0xc0, lsl #8
@@ -1659,7 +1659,7 @@ function x264_mbtree_propagate_list_internal_neon, export=1
     ret
 endfunc
 
-function x264_memcpy_aligned_neon, export=1
+function memcpy_aligned_neon, export=1
     tst         x2,  #16
     b.eq        32f
     sub         x2,  x2,  #16
@@ -1684,7 +1684,7 @@ function x264_memcpy_aligned_neon, export=1
     ret
 endfunc
 
-function x264_memzero_aligned_neon, export=1
+function memzero_aligned_neon, export=1
     movi        v0.16b,  #0
     movi        v1.16b,  #0
 1:
@@ -1698,7 +1698,7 @@ function x264_memzero_aligned_neon, export=1
 endfunc
 
 // void mbtree_fix8_pack( int16_t *dst, float *src, int count )
-function x264_mbtree_fix8_pack_neon, export=1
+function mbtree_fix8_pack_neon, export=1
     subs        w3,  w2,  #8
     b.lt        2f
 1:
@@ -1726,7 +1726,7 @@ function x264_mbtree_fix8_pack_neon, export=1
 endfunc
 
 // void mbtree_fix8_unpack( float *dst, int16_t *src, int count )
-function x264_mbtree_fix8_unpack_neon, export=1
+function mbtree_fix8_unpack_neon, export=1
     subs        w3,  w2,  #8
     b.lt        2f
 1:
diff --git a/common/aarch64/pixel-a.S b/common/aarch64/pixel-a.S
index 48209b2..ed64ad5 100644
--- a/common/aarch64/pixel-a.S
+++ b/common/aarch64/pixel-a.S
@@ -97,7 +97,7 @@ endconst
 .endm
 
 .macro SAD_FUNC w, h, name
-function x264_pixel_sad\name\()_\w\()x\h\()_neon, export=1
+function pixel_sad\name\()_\w\()x\h\()_neon, export=1
     SAD_START_\w
 
 .rept \h / 2 - 1
@@ -195,7 +195,7 @@ SAD_FUNC  16, 16
 .endm
 
 .macro SAD_X_FUNC x, w, h
-function x264_pixel_sad_x\x\()_\w\()x\h\()_neon, export=1
+function pixel_sad_x\x\()_\w\()x\h\()_neon, export=1
 .if \x == 3
     mov         x6,  x5
     mov         x5,  x4
@@ -249,7 +249,7 @@ SAD_X_FUNC  4, 16, 8
 SAD_X_FUNC  4, 16, 16
 
 
-function x264_pixel_vsad_neon, export=1
+function pixel_vsad_neon, export=1
     subs        w2,  w2,  #2
     ld1        {v0.16b},  [x0],  x1
     ld1        {v1.16b},  [x0],  x1
@@ -273,7 +273,7 @@ function x264_pixel_vsad_neon, export=1
     ret
 endfunc
 
-function x264_pixel_asd8_neon, export=1
+function pixel_asd8_neon, export=1
     sub         w4,  w4,  #2
     ld1        {v0.8b}, [x0], x1
     ld1        {v1.8b}, [x2], x3
@@ -379,7 +379,7 @@ endfunc
 .endm
 
 .macro SSD_FUNC w h
-function x264_pixel_ssd_\w\()x\h\()_neon, export=1
+function pixel_ssd_\w\()x\h\()_neon, export=1
     SSD_START_\w
 .rept \h-2
     SSD_\w
@@ -402,7 +402,7 @@ SSD_FUNC  16, 8
 SSD_FUNC  16, 16
 
 
-function x264_pixel_ssd_nv12_core_neon, export=1
+function pixel_ssd_nv12_core_neon, export=1
     sxtw        x8,  w4
     add         x8,  x8,  #8
     and         x8,  x8,  #~15
@@ -473,7 +473,7 @@ function x264_pixel_ssd_nv12_core_neon, export=1
 endfunc
 
 .macro pixel_var_8 h
-function x264_pixel_var_8x\h\()_neon, export=1
+function pixel_var_8x\h\()_neon, export=1
     ld1            {v16.8b}, [x0], x1
     ld1            {v17.8b}, [x0], x1
     mov             x2,  \h - 4
@@ -512,14 +512,14 @@ function x264_pixel_var_8x\h\()_neon, export=1
     uadalp          v1.4s,  v28.8h
     uadalp          v2.4s,  v29.8h
 
-    b               x264_var_end
+    b               var_end
 endfunc
 .endm
 
 pixel_var_8  8
 pixel_var_8 16
 
-function x264_pixel_var_16x16_neon, export=1
+function pixel_var_16x16_neon, export=1
     ld1            {v16.16b}, [x0],  x1
     ld1            {v17.16b}, [x0],  x1
     mov             x2,  #14
@@ -556,7 +556,7 @@ function x264_pixel_var_16x16_neon, export=1
     uadalp          v2.4s,  v4.8h
 endfunc
 
-function x264_var_end
+function var_end
     add             v1.4s,  v1.4s,  v2.4s
     uaddlv          s0,  v0.8h
     uaddlv          d1,  v1.4s
@@ -568,7 +568,7 @@ endfunc
 
 
 .macro pixel_var2_8 h
-function x264_pixel_var2_8x\h\()_neon, export=1
+function pixel_var2_8x\h\()_neon, export=1
     ld1            {v16.8b}, [x0], x1
     ld1            {v18.8b}, [x2], x3
     ld1            {v17.8b}, [x0], x1
@@ -629,7 +629,7 @@ pixel_var2_8  8
 pixel_var2_8 16
 
 
-function x264_pixel_satd_4x4_neon, export=1
+function pixel_satd_4x4_neon, export=1
     ld1        {v1.s}[0],  [x2], x3
     ld1        {v0.s}[0],  [x0], x1
     ld1        {v3.s}[0],  [x2], x3
@@ -662,7 +662,7 @@ function x264_pixel_satd_4x4_neon, export=1
     ret
 endfunc
 
-function x264_pixel_satd_4x8_neon, export=1
+function pixel_satd_4x8_neon, export=1
     ld1        {v1.s}[0],  [x2], x3
     ld1        {v0.s}[0],  [x0], x1
     ld1        {v3.s}[0],  [x2], x3
@@ -679,10 +679,10 @@ function x264_pixel_satd_4x8_neon, export=1
     ld1        {v4.s}[1],  [x0], x1
     ld1        {v7.s}[1],  [x2], x3
     ld1        {v6.s}[1],  [x0], x1
-    b           x264_satd_4x8_8x4_end_neon
+    b           satd_4x8_8x4_end_neon
 endfunc
 
-function x264_pixel_satd_8x4_neon, export=1
+function pixel_satd_8x4_neon, export=1
     ld1        {v1.8b},  [x2], x3
     ld1        {v0.8b},  [x0], x1
     ld1        {v3.8b},  [x2], x3
@@ -693,7 +693,7 @@ function x264_pixel_satd_8x4_neon, export=1
     ld1        {v6.8b},  [x0], x1
 endfunc
 
-function x264_satd_4x8_8x4_end_neon
+function satd_4x8_8x4_end_neon
     usubl       v0.8h,  v0.8b,  v1.8b
     usubl       v1.8h,  v2.8b,  v3.8b
     usubl       v2.8h,  v4.8b,  v5.8b
@@ -729,10 +729,10 @@ function x264_satd_4x8_8x4_end_neon
     ret
 endfunc
 
-function x264_pixel_satd_8x8_neon, export=1
+function pixel_satd_8x8_neon, export=1
     mov         x4,  x30
 
-    bl x264_satd_8x8_neon
+    bl satd_8x8_neon
     add         v0.8h,  v0.8h,  v1.8h
     add         v1.8h,  v2.8h,  v3.8h
     add         v0.8h,  v0.8h,  v1.8h
@@ -741,15 +741,15 @@ function x264_pixel_satd_8x8_neon, export=1
     ret         x4
 endfunc
 
-function x264_pixel_satd_8x16_neon, export=1
+function pixel_satd_8x16_neon, export=1
     mov         x4,  x30
 
-    bl x264_satd_8x8_neon
+    bl satd_8x8_neon
     add         v0.8h,  v0.8h,  v1.8h
     add         v1.8h,  v2.8h,  v3.8h
     add         v30.8h, v0.8h,  v1.8h
 
-    bl x264_satd_8x8_neon
+    bl satd_8x8_neon
     add         v0.8h,  v0.8h,  v1.8h
     add         v1.8h,  v2.8h,  v3.8h
     add         v31.8h, v0.8h,  v1.8h
@@ -805,12 +805,12 @@ endfunc
     SUMSUB_ABCD \r1, \r3, \r2, \r4, \t1, \t3, \t2, \t4
 .endm
 
-function x264_satd_8x8_neon
+function satd_8x8_neon
     load_diff_fly_8x8
 endfunc
 
 // one vertical hadamard pass and two horizontal
-function x264_satd_8x4v_8x8h_neon
+function satd_8x4v_8x8h_neon
     SUMSUB_AB   v16.8h, v18.8h, v0.8h,  v2.8h
     SUMSUB_AB   v17.8h, v19.8h, v1.8h,  v3.8h
 
@@ -848,14 +848,14 @@ function x264_satd_8x4v_8x8h_neon
     ret
 endfunc
 
-function x264_pixel_satd_16x8_neon, export=1
+function pixel_satd_16x8_neon, export=1
     mov         x4,  x30
 
-    bl          x264_satd_16x4_neon
+    bl          satd_16x4_neon
     add         v30.8h, v0.8h,  v1.8h
     add         v31.8h, v2.8h,  v3.8h
 
-    bl          x264_satd_16x4_neon
+    bl          satd_16x4_neon
     add         v0.8h,  v0.8h,  v1.8h
     add         v1.8h,  v2.8h,  v3.8h
     add         v30.8h, v30.8h, v0.8h
@@ -867,26 +867,26 @@ function x264_pixel_satd_16x8_neon, export=1
     ret         x4
 endfunc
 
-function x264_pixel_satd_16x16_neon, export=1
+function pixel_satd_16x16_neon, export=1
     mov         x4,  x30
 
-    bl          x264_satd_16x4_neon
+    bl          satd_16x4_neon
     add         v30.8h, v0.8h,  v1.8h
     add         v31.8h, v2.8h,  v3.8h
 
-    bl          x264_satd_16x4_neon
+    bl          satd_16x4_neon
     add         v0.8h,  v0.8h,  v1.8h
     add         v1.8h,  v2.8h,  v3.8h
     add         v30.8h, v30.8h, v0.8h
     add         v31.8h, v31.8h, v1.8h
 
-    bl          x264_satd_16x4_neon
+    bl          satd_16x4_neon
     add         v0.8h,  v0.8h,  v1.8h
     add         v1.8h,  v2.8h,  v3.8h
     add         v30.8h, v30.8h, v0.8h
     add         v31.8h, v31.8h, v1.8h
 
-    bl          x264_satd_16x4_neon
+    bl          satd_16x4_neon
     add         v0.8h,  v0.8h,  v1.8h
     add         v1.8h,  v2.8h,  v3.8h
     add         v30.8h, v30.8h, v0.8h
@@ -898,7 +898,7 @@ function x264_pixel_satd_16x16_neon, export=1
     ret         x4
 endfunc
 
-function x264_satd_16x4_neon
+function satd_16x4_neon
     ld1        {v1.16b},  [x2], x3
     ld1        {v0.16b},  [x0], x1
     ld1        {v3.16b},  [x2], x3
@@ -920,10 +920,10 @@ function x264_satd_16x4_neon
     SUMSUB_AB   v0.8h,  v1.8h,  v16.8h, v17.8h
     SUMSUB_AB   v2.8h,  v3.8h,  v18.8h, v19.8h
 
-    b           x264_satd_8x4v_8x8h_neon
+    b           satd_8x4v_8x8h_neon
 endfunc
 
-function x264_pixel_satd_4x16_neon, export=1
+function pixel_satd_4x16_neon, export=1
     mov         x4,  x30
     ld1        {v1.s}[0],  [x2], x3
     ld1        {v0.s}[0],  [x0], x1
@@ -969,7 +969,7 @@ function x264_pixel_satd_4x16_neon, export=1
     SUMSUB_AB   v0.8h,  v1.8h,  v16.8h, v17.8h
     SUMSUB_AB   v2.8h,  v3.8h,  v18.8h, v19.8h
 
-    bl          x264_satd_8x4v_8x8h_neon
+    bl          satd_8x4v_8x8h_neon
 
     add         v30.8h, v0.8h,  v1.8h
     add         v31.8h, v2.8h,  v3.8h
@@ -979,7 +979,7 @@ function x264_pixel_satd_4x16_neon, export=1
     ret         x4
 endfunc
 
-function x264_pixel_sa8d_8x8_neon, export=1
+function pixel_sa8d_8x8_neon, export=1
     mov         x4,  x30
     bl          pixel_sa8d_8x8_neon
     add         v0.8h,  v0.8h,  v1.8h
@@ -990,7 +990,7 @@ function x264_pixel_sa8d_8x8_neon, export=1
     ret         x4
 endfunc
 
-function x264_pixel_sa8d_16x16_neon, export=1
+function pixel_sa8d_16x16_neon, export=1
     mov         x4,  x30
     bl          pixel_sa8d_8x8_neon
     uaddlp      v30.4s, v0.8h
@@ -1112,7 +1112,7 @@ endfunc
 sa8d_satd_8x8
 sa8d_satd_8x8 satd_
 
-function x264_pixel_sa8d_satd_16x16_neon, export=1
+function pixel_sa8d_satd_16x16_neon, export=1
     mov         x4,  x30
     bl          pixel_sa8d_satd_8x8_neon
     uaddlp      v30.4s, v0.8h
@@ -1150,25 +1150,25 @@ function x264_pixel_sa8d_satd_16x16_neon, export=1
 endfunc
 
 .macro HADAMARD_AC w h
-function x264_pixel_hadamard_ac_\w\()x\h\()_neon, export=1
+function pixel_hadamard_ac_\w\()x\h\()_neon, export=1
     movrel      x5, mask_ac_4_8
     mov         x4,  x30
     ld1         {v30.8h,v31.8h}, [x5]
     movi        v28.16b, #0
     movi        v29.16b, #0
 
-    bl          x264_hadamard_ac_8x8_neon
+    bl          hadamard_ac_8x8_neon
 .if \h > 8
-    bl          x264_hadamard_ac_8x8_neon
+    bl          hadamard_ac_8x8_neon
 .endif
 .if \w > 8
     sub         x0,  x0,  x1,  lsl #3
     add         x0,  x0,  #8
-    bl          x264_hadamard_ac_8x8_neon
+    bl          hadamard_ac_8x8_neon
 .endif
 .if \w * \h == 256
     sub         x0,  x0,  x1,  lsl #4
-    bl          x264_hadamard_ac_8x8_neon
+    bl          hadamard_ac_8x8_neon
 .endif
 
     addv        s1,  v29.4s
@@ -1188,7 +1188,7 @@ HADAMARD_AC 16, 8
 HADAMARD_AC 16, 16
 
 // v28: satd  v29: sa8d  v30: mask_ac4  v31: mask_ac8
-function x264_hadamard_ac_8x8_neon
+function hadamard_ac_8x8_neon
     ld1         {v16.8b}, [x0], x1
     ld1         {v17.8b}, [x0], x1
     ld1         {v18.8b}, [x0], x1
@@ -1280,7 +1280,7 @@ function x264_hadamard_ac_8x8_neon
 endfunc
 
 
-function x264_pixel_ssim_4x4x2_core_neon, export=1
+function pixel_ssim_4x4x2_core_neon, export=1
     ld1        {v0.8b},  [x0], x1
     ld1        {v2.8b},  [x2], x3
     umull       v16.8h, v0.8b,  v0.8b
@@ -1339,7 +1339,7 @@ function x264_pixel_ssim_4x4x2_core_neon, export=1
     ret
 endfunc
 
-function x264_pixel_ssim_end4_neon, export=1
+function pixel_ssim_end4_neon, export=1
     mov         x5,  #4
     ld1        {v16.4s,v17.4s}, [x0], #32
     ld1        {v18.4s,v19.4s}, [x1], #32
diff --git a/common/aarch64/predict-a.S b/common/aarch64/predict-a.S
index e5d2e2b..d287b12 100644
--- a/common/aarch64/predict-a.S
+++ b/common/aarch64/predict-a.S
@@ -62,7 +62,7 @@ endconst
 .endm
 
 
-function x264_predict_4x4_h_aarch64, export=1
+function predict_4x4_h_aarch64, export=1
     ldrb    w1,  [x0, #0*FDEC_STRIDE-1]
     mov     w5,  #0x01010101
     ldrb    w2,  [x0, #1*FDEC_STRIDE-1]
@@ -79,7 +79,7 @@ function x264_predict_4x4_h_aarch64, export=1
     ret
 endfunc
 
-function x264_predict_4x4_v_aarch64, export=1
+function predict_4x4_v_aarch64, export=1
     ldr     w1,  [x0, #0 - 1 * FDEC_STRIDE]
     str     w1,  [x0, #0 + 0 * FDEC_STRIDE]
     str     w1,  [x0, #0 + 1 * FDEC_STRIDE]
@@ -88,7 +88,7 @@ function x264_predict_4x4_v_aarch64, export=1
     ret
 endfunc
 
-function x264_predict_4x4_dc_neon, export=1
+function predict_4x4_dc_neon, export=1
     sub         x1,  x0,  #FDEC_STRIDE
     ldrb        w4,  [x0, #-1 + 0 * FDEC_STRIDE]
     ldrb        w5,  [x0, #-1 + 1 * FDEC_STRIDE]
@@ -110,7 +110,7 @@ function x264_predict_4x4_dc_neon, export=1
     ret
 endfunc
 
-function x264_predict_4x4_dc_top_neon, export=1
+function predict_4x4_dc_top_neon, export=1
     sub         x1,  x0,  #FDEC_STRIDE
     ldr         s0, [x1]
     uaddlv      h0,  v0.8b
@@ -124,7 +124,7 @@ function x264_predict_4x4_dc_top_neon, export=1
     ret
 endfunc
 
-function x264_predict_4x4_ddr_neon, export=1
+function predict_4x4_ddr_neon, export=1
     sub         x1,  x0,  #FDEC_STRIDE+1
     mov         x7,  #FDEC_STRIDE
     ld1        {v0.8b}, [x1], x7            // # -FDEC_STRIDE-1
@@ -152,7 +152,7 @@ function x264_predict_4x4_ddr_neon, export=1
     ret
 endfunc
 
-function x264_predict_4x4_ddl_neon, export=1
+function predict_4x4_ddl_neon, export=1
     sub         x0,  x0,  #FDEC_STRIDE
     mov         x7,  #FDEC_STRIDE
     ld1        {v0.8b}, [x0],  x7
@@ -171,7 +171,7 @@ function x264_predict_4x4_ddl_neon, export=1
     ret
 endfunc
 
-function x264_predict_8x8_dc_neon, export=1
+function predict_8x8_dc_neon, export=1
     mov         x7,  #FDEC_STRIDE
     ld1        {v0.16b}, [x1], #16
     ld1        {v1.8b},  [x1]
@@ -187,7 +187,7 @@ function x264_predict_8x8_dc_neon, export=1
     ret
 endfunc
 
-function x264_predict_8x8_h_neon, export=1
+function predict_8x8_h_neon, export=1
     mov         x7,  #FDEC_STRIDE
     ld1        {v16.16b}, [x1]
     dup         v0.8b, v16.b[14]
@@ -209,7 +209,7 @@ function x264_predict_8x8_h_neon, export=1
     ret
 endfunc
 
-function x264_predict_8x8_v_neon, export=1
+function predict_8x8_v_neon, export=1
     add         x1,  x1,  #16
     mov         x7,  #FDEC_STRIDE
     ld1        {v0.8b}, [x1]
@@ -219,7 +219,7 @@ function x264_predict_8x8_v_neon, export=1
     ret
 endfunc
 
-function x264_predict_8x8_ddl_neon, export=1
+function predict_8x8_ddl_neon, export=1
     add         x1,  x1,  #16
     mov         x7,  #FDEC_STRIDE
     ld1        {v0.16b}, [x1]
@@ -248,7 +248,7 @@ function x264_predict_8x8_ddl_neon, export=1
     ret
 endfunc
 
-function x264_predict_8x8_ddr_neon, export=1
+function predict_8x8_ddr_neon, export=1
     ld1        {v0.16b,v1.16b}, [x1]
     ext         v2.16b, v0.16b, v1.16b, #7
     ext         v4.16b, v0.16b, v1.16b, #9
@@ -278,7 +278,7 @@ function x264_predict_8x8_ddr_neon, export=1
     ret
 endfunc
 
-function x264_predict_8x8_vl_neon, export=1
+function predict_8x8_vl_neon, export=1
     add         x1,  x1,  #16
     mov         x7, #FDEC_STRIDE
 
@@ -309,7 +309,7 @@ function x264_predict_8x8_vl_neon, export=1
     ret
 endfunc
 
-function x264_predict_8x8_vr_neon, export=1
+function predict_8x8_vr_neon, export=1
     add         x1,  x1,  #8
     mov         x7,  #FDEC_STRIDE
     ld1        {v2.16b}, [x1]
@@ -343,7 +343,7 @@ function x264_predict_8x8_vr_neon, export=1
     ret
 endfunc
 
-function x264_predict_8x8_hd_neon, export=1
+function predict_8x8_hd_neon, export=1
     add         x1,  x1,  #7
     mov         x7, #FDEC_STRIDE
 
@@ -378,7 +378,7 @@ function x264_predict_8x8_hd_neon, export=1
     ret
 endfunc
 
-function x264_predict_8x8_hu_neon, export=1
+function predict_8x8_hu_neon, export=1
     add         x1,  x1,  #7
     mov         x7,  #FDEC_STRIDE
     ld1        {v7.8b}, [x1]
@@ -416,7 +416,7 @@ function x264_predict_8x8_hu_neon, export=1
 endfunc
 
 
-function x264_predict_8x8c_dc_top_neon, export=1
+function predict_8x8c_dc_top_neon, export=1
     sub         x2,  x0,  #FDEC_STRIDE
     mov         x1,  #FDEC_STRIDE
     ld1        {v0.8b},  [x2]
@@ -429,7 +429,7 @@ function x264_predict_8x8c_dc_top_neon, export=1
     b           pred8x8c_dc_end
 endfunc
 
-function x264_predict_8x8c_dc_left_neon, export=1
+function predict_8x8c_dc_left_neon, export=1
     ldrb        w2,  [x0, #0 * FDEC_STRIDE - 1]
     ldrb        w3,  [x0, #1 * FDEC_STRIDE - 1]
     ldrb        w4,  [x0, #2 * FDEC_STRIDE - 1]
@@ -452,7 +452,7 @@ function x264_predict_8x8c_dc_left_neon, export=1
     b           pred8x8c_dc_end
 endfunc
 
-function x264_predict_8x8c_dc_neon, export=1
+function predict_8x8c_dc_neon, export=1
     mov         x1,  #FDEC_STRIDE
     sub         x2,  x0,  #FDEC_STRIDE
     ldrb        w10, [x0, #0 * FDEC_STRIDE - 1]
@@ -498,7 +498,7 @@ pred8x8c_dc_end:
     ret
 endfunc
 
-function x264_predict_8x8c_h_neon, export=1
+function predict_8x8c_h_neon, export=1
     sub         x1,  x0,  #1
     mov         x7,  #FDEC_STRIDE
 .rept 4
@@ -510,7 +510,7 @@ function x264_predict_8x8c_h_neon, export=1
     ret
 endfunc
 
-function x264_predict_8x8c_v_aarch64, export=1
+function predict_8x8c_v_aarch64, export=1
     ldr         x1,  [x0, #-FDEC_STRIDE]
 .irp c, 0,1,2,3,4,5,6,7
     str         x1,  [x0, #\c * FDEC_STRIDE]
@@ -518,7 +518,7 @@ function x264_predict_8x8c_v_aarch64, export=1
     ret
 endfunc
 
-function x264_predict_8x8c_p_neon, export=1
+function predict_8x8c_p_neon, export=1
     sub         x3,  x0,  #FDEC_STRIDE
     mov         x1,  #FDEC_STRIDE
     add         x2,  x3,  #4
@@ -577,7 +577,7 @@ endfunc
     add         \wd,  \wd,  \t1
 .endm
 
-function x264_predict_8x16c_h_neon, export=1
+function predict_8x16c_h_neon, export=1
     sub         x2,  x0,  #1
     add         x3,  x0,  #FDEC_STRIDE - 1
     mov         x7,  #2 * FDEC_STRIDE
@@ -595,7 +595,7 @@ function x264_predict_8x16c_h_neon, export=1
     ret
 endfunc
 
-function x264_predict_8x16c_v_neon, export=1
+function predict_8x16c_v_neon, export=1
     sub         x1,  x0,  #FDEC_STRIDE
     mov         x2,  #2 * FDEC_STRIDE
     ld1        {v0.8b}, [x1], x2
@@ -606,7 +606,7 @@ function x264_predict_8x16c_v_neon, export=1
     ret
 endfunc
 
-function x264_predict_8x16c_p_neon, export=1
+function predict_8x16c_p_neon, export=1
     movrel      x4,  p16weight
     ld1        {v17.8h}, [x4]
     sub         x3,  x0,  #FDEC_STRIDE
@@ -673,7 +673,7 @@ function x264_predict_8x16c_p_neon, export=1
     ret
 endfunc
 
-function x264_predict_8x16c_dc_neon, export=1
+function predict_8x16c_dc_neon, export=1
     mov         x1,  #FDEC_STRIDE
     sub         x10, x0,  #FDEC_STRIDE
     loadsum4    w2, w3, w4, w5, x0, 0
@@ -718,7 +718,7 @@ function x264_predict_8x16c_dc_neon, export=1
     ret
 endfunc
 
-function x264_predict_8x16c_dc_left_neon, export=1
+function predict_8x16c_dc_left_neon, export=1
     mov         x1,  #FDEC_STRIDE
     ldrb        w2,  [x0, # 0 * FDEC_STRIDE - 1]
     ldrb        w3,  [x0, # 1 * FDEC_STRIDE - 1]
@@ -772,7 +772,7 @@ function x264_predict_8x16c_dc_left_neon, export=1
     ret
 endfunc
 
-function x264_predict_8x16c_dc_top_neon, export=1
+function predict_8x16c_dc_top_neon, export=1
     sub         x2,  x0,  #FDEC_STRIDE
     mov         x1,  #FDEC_STRIDE
     ld1        {v0.8b}, [x2]
@@ -789,7 +789,7 @@ function x264_predict_8x16c_dc_top_neon, export=1
 endfunc
 
 
-function x264_predict_16x16_dc_top_neon, export=1
+function predict_16x16_dc_top_neon, export=1
     sub         x2,  x0,  #FDEC_STRIDE
     mov         x1,  #FDEC_STRIDE
     ld1        {v0.16b}, [x2]
@@ -799,7 +799,7 @@ function x264_predict_16x16_dc_top_neon, export=1
     b           pred16x16_dc_end
 endfunc
 
-function x264_predict_16x16_dc_left_neon, export=1
+function predict_16x16_dc_left_neon, export=1
     sub         x2,  x0,  #1
     mov         x1,  #FDEC_STRIDE
     ldcol.16    v0,  x2,  x1
@@ -809,7 +809,7 @@ function x264_predict_16x16_dc_left_neon, export=1
     b           pred16x16_dc_end
 endfunc
 
-function x264_predict_16x16_dc_neon, export=1
+function predict_16x16_dc_neon, export=1
     sub         x3,  x0,  #FDEC_STRIDE
     sub         x2,  x0,  #1
     mov         x1,  #FDEC_STRIDE
@@ -827,7 +827,7 @@ pred16x16_dc_end:
     ret
 endfunc
 
-function x264_predict_16x16_h_neon, export=1
+function predict_16x16_h_neon, export=1
     sub         x1,  x0,  #1
     mov         x7, #FDEC_STRIDE
 .rept 8
@@ -839,7 +839,7 @@ function x264_predict_16x16_h_neon, export=1
     ret
 endfunc
 
-function x264_predict_16x16_v_neon, export=1
+function predict_16x16_v_neon, export=1
     sub         x0,  x0,  #FDEC_STRIDE
     mov         x7,  #FDEC_STRIDE
     ld1        {v0.16b}, [x0], x7
@@ -849,7 +849,7 @@ function x264_predict_16x16_v_neon, export=1
     ret
 endfunc
 
-function x264_predict_16x16_p_neon, export=1
+function predict_16x16_p_neon, export=1
     sub         x3,  x0,  #FDEC_STRIDE
     mov         x1,  #FDEC_STRIDE
     add         x2,  x3,  #8
diff --git a/common/aarch64/quant-a.S b/common/aarch64/quant-a.S
index 21ecb4b..865e896 100644
--- a/common/aarch64/quant-a.S
+++ b/common/aarch64/quant-a.S
@@ -57,7 +57,7 @@
 .endm
 
 // quant_2x2_dc( int16_t dct[4], int mf, int bias )
-function x264_quant_2x2_dc_neon, export=1
+function quant_2x2_dc_neon, export=1
     ld1        {v0.4h}, [x0]
     dup         v2.4h,  w2
     dup         v1.4h,  w1
@@ -73,7 +73,7 @@ function x264_quant_2x2_dc_neon, export=1
 endfunc
 
 // quant_4x4_dc( int16_t dct[16], int mf, int bias )
-function x264_quant_4x4_dc_neon, export=1
+function quant_4x4_dc_neon, export=1
     ld1        {v16.8h,v17.8h}, [x0]
     abs         v18.8h,  v16.8h
     abs         v19.8h,  v17.8h
@@ -85,7 +85,7 @@ function x264_quant_4x4_dc_neon, export=1
 endfunc
 
 // quant_4x4( int16_t dct[16], uint16_t mf[16], uint16_t bias[16] )
-function x264_quant_4x4_neon, export=1
+function quant_4x4_neon, export=1
     ld1        {v16.8h,v17.8h}, [x0]
     abs         v18.8h,  v16.8h
     abs         v19.8h,  v17.8h
@@ -97,7 +97,7 @@ function x264_quant_4x4_neon, export=1
 endfunc
 
 // quant_4x4x4( int16_t dct[4][16], uint16_t mf[16], uint16_t bias[16] )
-function x264_quant_4x4x4_neon, export=1
+function quant_4x4x4_neon, export=1
     ld1        {v16.8h,v17.8h}, [x0]
     abs         v18.8h, v16.8h
     abs         v19.8h, v17.8h
@@ -140,7 +140,7 @@ function x264_quant_4x4x4_neon, export=1
 endfunc
 
 // quant_8x8( int16_t dct[64], uint16_t mf[64], uint16_t bias[64] )
-function x264_quant_8x8_neon, export=1
+function quant_8x8_neon, export=1
     ld1        {v16.8h,v17.8h}, [x0]
     abs         v18.8h, v16.8h
     abs         v19.8h, v17.8h
@@ -177,7 +177,7 @@ endfunc
 
 // dequant_4x4( int16_t dct[16], int dequant_mf[6][16], int i_qp )
 .macro DEQUANT size bits
-function x264_dequant_\size\()_neon, export=1
+function dequant_\size\()_neon, export=1
     DEQUANT_START \bits+2, \bits
 .ifc \size, 8x8
     mov         w2,  #4
@@ -258,7 +258,7 @@ DEQUANT 4x4, 4
 DEQUANT 8x8, 6
 
 // dequant_4x4_dc( int16_t dct[16], int dequant_mf[6][16], int i_qp )
-function x264_dequant_4x4_dc_neon, export=1
+function dequant_4x4_dc_neon, export=1
     DEQUANT_START 6, 6, yes
     b.lt        dequant_4x4_dc_rshift
 
@@ -303,9 +303,9 @@ dequant_4x4_dc_rshift:
 endfunc
 
 .macro decimate_score_1x size
-function x264_decimate_score\size\()_neon, export=1
+function decimate_score\size\()_neon, export=1
     ld1        {v0.8h,v1.8h}, [x0]
-    movrel      x5,  X(x264_decimate_table4)
+    movrel      x5,  X(decimate_table4)
     movi        v3.16b, #0x01
     sqxtn       v0.8b,  v0.8h
     sqxtn2      v0.16b, v1.8h
@@ -348,7 +348,7 @@ const mask64, align=6
     .byte  0x80, 0x40, 0x20, 0x10, 0x08, 0x04, 0x02, 0x01
 endconst
 
-function x264_decimate_score64_neon, export=1
+function decimate_score64_neon, export=1
     ld1        {v0.8h,v1.8h}, [x0], #32
     ld1        {v2.8h,v3.8h}, [x0], #32
     ld1        {v4.8h,v5.8h}, [x0], #32
@@ -391,7 +391,7 @@ function x264_decimate_score64_neon, export=1
     mvn         x1,  x1
     mov         w0,  #0
     cbz         x1,  0f
-    movrel      x5,  X(x264_decimate_table8)
+    movrel      x5,  X(decimate_table8)
 1:
     clz         x3,  x1
     lsl         x1,  x1,  x3
@@ -407,7 +407,7 @@ function x264_decimate_score64_neon, export=1
 endfunc
 
 // int coeff_last( int16_t *l )
-function x264_coeff_last4_aarch64, export=1
+function coeff_last4_aarch64, export=1
     ldr         x2,  [x0]
     mov         w4,  #3
     clz         x0,  x2
@@ -415,7 +415,7 @@ function x264_coeff_last4_aarch64, export=1
     ret
 endfunc
 
-function x264_coeff_last8_aarch64, export=1
+function coeff_last8_aarch64, export=1
     ldr         x3,  [x0, #8]
     mov         w4,  #7
     clz         x2,  x3
@@ -430,7 +430,7 @@ function x264_coeff_last8_aarch64, export=1
 endfunc
 
 .macro COEFF_LAST_1x size
-function x264_coeff_last\size\()_neon, export=1
+function coeff_last\size\()_neon, export=1
 .if \size == 15
     sub         x0,  x0,  #2
 .endif
@@ -450,7 +450,7 @@ endfunc
 COEFF_LAST_1x 15
 COEFF_LAST_1x 16
 
-function x264_coeff_last64_neon, export=1
+function coeff_last64_neon, export=1
     ld1        {v0.8h,v1.8h,v2.8h,v3.8h}, [x0], 64
     movi        v31.8h,  #8
     movi        v30.8h,  #1
@@ -523,7 +523,7 @@ endfunc
     mov         w0,  w7
 .endm
 
-function x264_coeff_level_run4_aarch64, export=1
+function coeff_level_run4_aarch64, export=1
     ldr         x2,  [x0]
 
     coeff_level_run_start 4
@@ -533,8 +533,8 @@ function x264_coeff_level_run4_aarch64, export=1
     ret
 endfunc
 
-.macro X264_COEFF_LEVEL_RUN size
-function x264_coeff_level_run\size\()_neon, export=1
+.macro COEFF_LEVEL_RUN size
+function coeff_level_run\size\()_neon, export=1
 .if \size == 15
     sub         x0,  x0,  #2
 .endif
@@ -562,11 +562,11 @@ function x264_coeff_level_run\size\()_neon, export=1
 endfunc
 .endm
 
-X264_COEFF_LEVEL_RUN 8
-X264_COEFF_LEVEL_RUN 15
-X264_COEFF_LEVEL_RUN 16
+COEFF_LEVEL_RUN 8
+COEFF_LEVEL_RUN 15
+COEFF_LEVEL_RUN 16
 
-function x264_denoise_dct_neon, export=1
+function denoise_dct_neon, export=1
 1:  subs        w3,  w3,  #16
     ld1         {v0.8h,v1.8h}, [x0]
     ld1         {v4.4s,v5.4s,v6.4s,v7.4s}, [x1]
diff --git a/tools/checkasm-aarch64.S b/tools/checkasm-aarch64.S
index 0341a5a..5e023c6 100644
--- a/tools/checkasm-aarch64.S
+++ b/tools/checkasm-aarch64.S
@@ -58,7 +58,7 @@ error_message:
 
 #define CLOBBER_STACK ((8*MAX_ARGS + 15) & ~15)
 
-function x264_checkasm_stack_clobber, export=1
+function checkasm_stack_clobber, export=1
     mov         x3,  sp
     mov         x2,  #CLOBBER_STACK
 1:
@@ -71,7 +71,7 @@ endfunc
 
 #define ARG_STACK ((8*(MAX_ARGS - 8) + 15) & ~15)
 
-function x264_checkasm_call, export=1
+function checkasm_call, export=1
     stp         x29, x30, [sp, #-16]!
     mov         x29, sp
     stp         x19, x20, [sp, #-16]!
-- 
2.10.0



More information about the x264-devel mailing list